English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Accurate pedestrian trajectory prediction is of great importance fordownstream tasks such as autonomous driving and mobile robot navigation. Fullyinvestigating the social interactions within the crowd is crucial for accuratepedestrian trajectory prediction. However, most existing methods do not capturegroup level interactions well, focusing only on pairwise interactions andneglecting group-wise interactions. In this work, we propose a hierarchicalgraph convolutional network, HGCN-GJS, for trajectory prediction which wellleverages group level interactions within the crowd. Furthermore, we introducea novel joint sampling scheme for modeling the joint distribution of multiplepedestrians in the future trajectories. Based on the group information, thisscheme associates the trajectory of one person with the trajectory of otherpeople in the group, but maintains the independence of the trajectories ofoutsiders. We demonstrate the performance of our network on several trajectoryprediction datasets, achieving state-of-the-art results on all datasetsconsidered.

HGCN-GJS: Hierarchical Graph Convolutional Network with Groupwise Joint Sampling for Trajectory Prediction